memory-management

Decode shorthand and acronyms into structured actions in Obsidian vaults.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/tsemana/obsidian-productivity --skill memory-management-tsemana
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-management
Source: https://github.com/tsemana/obsidian-productivity/tree/main/plugin/skills/memory-management
Command: npx skills add https://github.com/tsemana/obsidian-productivity --skill memory-management-tsemana

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would, enabling reliable collaboration in an Obsidian vault.

Core Features & Use Cases

  • A two-tier memory model with a hot CLAUDE.md cache and a full memory/ knowledge base for long-tail queries.
  • Obsidian-friendly memory notes (memory/glossary.md, memory/people/, memory/projects/, memory/context/) that plug into wikilinks and frontmatter.
  • Dual-context support for work and personal vaults, with context tagging and cross-context lookups.

Quick Start

In the current vault, ask Claude to decode a term like PSR to its full meaning.

Frequently Asked Questions about memory-management

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make Claude understand internal shorthand and acronyms inside an Obsidian vault?

To decode internal shorthand inside an Obsidian vault, you need a memory layer that maps acronyms to full meanings. This Skill uses a glossary file and context directory to resolve workplace shorthand so Claude interprets requests like a colleague.

What is the best way to maintain persistent context for people and projects in Obsidian notes?

Maintaining persistent context for people and projects requires structured memory directories. This Skill organizes notes into memory/people/ and memory/projects/ folders with frontmatter and wikilinks, allowing Claude to retrieve accurate background information on demand.

Can I use a single memory system to manage both work and personal Obsidian vaults?

Yes, you can manage dual-context vaults using this Skill. It supports context tagging and cross-context lookups, enabling Claude to distinguish between work and personal projects while querying the unified memory knowledge base.

How does Claude retrieve long-tail context without reading the entire vault each time?

Claude retrieves long-tail context using a two-tier memory model. A hot CLAUDE.md cache provides fast access to immediate instructions, while a dedicated memory/ directory stores deeper knowledge for slower, comprehensive queries.

Do I need specific folder structures to enable memory lookups with wikilinks and frontmatter?

Yes, memory lookups require specific folder structures. The Skill relies on a memory/ directory containing glossary.md and subdirectories for people, projects, and context, integrating Obsidian frontmatter and wikilinks for structured retrieval.